Sleep disorders related to deployment in active duty service members and veterans

Toward personalized care for insomnia in the US Army: a machine learning model to predict response to cognitive behavioral therapy for insomnia

STUDY OBJECTIVES

The standard of care for military personnel with insomnia is cognitive behavioral therapy for insomnia (CBT-I). However, only a minority seeking insomnia treatment receive CBT-I, and little reliable guidance exists to identify those most likely to respond. As a step toward personalized care, we present results of a machine learning (ML) model to predict CBT-I response.

METHODS

Administrative data were examined for n = 1,449 nondeployed US Army soldiers treated for insomnia with CBT-I who had moderate-severe baseline Insomnia Severity Index (ISI) scores and completed 1 or more follow-up ISIs 6-12 weeks after baseline. An ensemble ML model was developed in a 70% training sample to predict clinically significant ISI improvement (reduction of at least 2 standard deviations on the baseline ISI distribution). Predictors included a wide range of military administrative and baseline clinical variables. Model accuracy was evaluated in the remaining 30% test sample.

RESULTS

19.8% of patients had clinically significant ISI improvement. Model area under the receiver operating characteristic curve (standard error) was 0.60 (0.03). The 20% of test-sample patients with the highest probabilities of improvement were twice as likely to have clinically significant improvement compared with the remaining 80% (36.5% vs 15.7%; χ21 = 9.2, P = .002). Nearly 85% of prediction accuracy was due to 10 variables, the most important of which were baseline insomnia severity and baseline suicidal ideation.

CONCLUSIONS

Pending replication, the model could be used as part of a patient-centered decision-making process for insomnia treatment. Parallel models will be needed for alternative treatments before such a system is of optimal value.

CITATION

Gabbay FH, Wynn GH, Georg MW, et al. Toward personalized care for insomnia in the US Army: a machine learning model to predict response to cognitive behavioral therapy for insomnia. J Clin Sleep Med. 2024;20(6):921-931.

Health behavior profiles and association with mental health status among US active-duty service members

Introduction

This study investigated the clustering of health behaviors among US active duty servicemembers (ADSM) into risk profiles and explored the association between these profiles with ADSM sociodemographic characteristics and mental health status.

Methods

This study utilized secondary data from the 2018 Health Related Behaviors Survey (HRBS), a Department of Defense (DoD) self-administered online survey. Health behaviors included physical activity, screen use, sleep habits, tobacco/substance use, alcohol drinking, preventive health care seeking and condom use at last sex/having multiple sexual partners. Past-year mental health status was measured using the Kessler Screening Scale for Psychological Distress (K6). Latent class analysis (LCA) on health behaviors was used to cluster ADSMs into risk profiles. Multivariable logistic model was used to examine whether ADSM characteristics and mental health status were associated with ADSMs' risk profiles.

Results

The LCA identified a four-class model that clustered ADSMs into the following sub-groups: (1) Risk Inclined (14.4%), (2) High Screen Users (51.1%), (3) Poor Sleepers (23.9%) and (4) Risk Averse (10.6). Over a tenth (16.4%) of ADSMs were categorized as having serious psychological distress. Being male, younger, less educated, in the Army, Marine Corps or Navy were associated with higher odds of being Risk Inclined (AOR ranging from 1.26 to 2.42). Compared to the reference group of Risk Adverse ADSMs, those categorized as Risk Inclined (AOR: 8.30; 95% CI: 5.16-13.36), High Screen Users (AOR: 2.44; 95% CI: 1.56-3.82) and Poor Sleepers (AOR: 5.26; 95% CI: 3.38-8.19) had significantly higher odds of having serious psychological distress.

Discussion

Study findings suggest opportunities to tailor behavioral and health promotion interventions for each of the distinct risk profiles. For example, ADSM described as Risk Inclined may benefit from preventive mental health services. Solutions for ADSM described as Poor Sleepers may include education on sleep hygiene; instituting duty schedules; and shifting military cultural norms to promote sleep hygiene as a pathway to optimal performance and thus military readiness. ADSM with low-risk behavior profiles such as those described as Risk Averse may prove beneficial in the roll-out of interventions as they act as peer-educators or mentors.

Toward personalized care for insomnia in the US Army: development of a machine-learning model to predict response to pharmacotherapy

STUDY OBJECTIVES

Although many military personnel with insomnia are treated with prescription medication, little reliable guidance exists to identify patients most likely to respond. As a first step toward personalized care for insomnia, we present results of a machine-learning model to predict response to insomnia medication.

METHODS

The sample comprised n = 4,738 nondeployed US Army soldiers treated with insomnia medication and followed 6-12 weeks after initiating treatment. All patients had moderate-severe baseline scores on the Insomnia Severity Index (ISI) and completed 1 or more follow-up ISIs 6-12 weeks after baseline. An ensemble machine-learning model was developed in a 70% training sample to predict clinically significant ISI improvement, defined as reduction of at least 2 standard deviations on the baseline ISI distribution. Predictors included a wide range of military administrative and baseline clinical variables. Model accuracy was evaluated in the remaining 30% test sample.

RESULTS

21.3% of patients had clinically significant ISI improvement. Model test sample area under the receiver operating characteristic curve (standard error) was 0.63 (0.02). Among the 30% of patients with the highest predicted probabilities of improvement, 32.5.% had clinically significant symptom improvement vs 16.6% in the 70% sample predicted to be least likely to improve (χ21 = 37.1, P < .001). More than 75% of prediction accuracy was due to 10 variables, the most important of which was baseline insomnia severity.

CONCLUSIONS

Pending replication, the model could be used as part of a patient-centered decision-making process for insomnia treatment, but parallel models will be needed for alternative treatments before such a system is of optimal value.

CITATION

Gabbay FH, Wynn GH, Georg MW, et al. Toward personalized care for insomnia in the US Army: development of a machine-learning model to predict response to pharmacotherapy. J Clin Sleep Med. 2023;19(8):1399-1410.

The bi-directional relationship between post-traumatic stress disorder and obstructive sleep apnea and/or insomnia in a large U.S. military cohort

OBJECTIVES

Determine if a bi-directional relationship exists between the development of sleep disorders (obstructive sleep apnea [OSA] and/or insomnia) and existing post-traumatic stress disorder (PTSD), and vice versa; and examine military-related factors associated with these potential relationships.

DESIGN

Longitudinal analyses of a prospective representative U.S. military cohort.

PARTICIPANTS

Millennium Cohort Study responders in 2011-2013 (Time 1 [T1]) and 2014-2016 (Time 2 [T2]) without insomnia or OSA at T1 (N = 65,915) or without PTSD at T1 (N = 71,256).

MEASUREMENTS

Provider-diagnosed OSA, self-reported items for insomnia, provider-diagnosed PTSD, and current PTSD symptoms were assessed at T1 and T2. Adjusted multivariable models identified military-related factors associated with new-onset PTSD in those with OSA and/or insomnia, and vice versa.

RESULTS

Self-reported history of provider-diagnosed PTSD without current symptoms at T1 was associated with new-onset OSA only and comorbid OSA/insomnia at T2, while current PTSD symptoms and/or diagnosis was associated with new-onset insomnia only. OSA/insomnia at T1 was consistently associated with newly reported PTSD symptoms or diagnosis except that insomnia only was not associated with newly reported provider-diagnosed PTSD. Military-related risk factors significantly associated with the bi-directional relationship for new-onset PTSD or OSA/insomnia included prior deployment with higher combat exposure and recent separation from the military; being an officer was protective for both outcomes.

CONCLUSIONS

In this large military cohort, findings suggest that PTSD and OSA and/or insomnia are bi-directionally predictive for their development, which was sometimes revealed by health care utilization. Relevant military-related risk factors should be considered in efforts to prevent or treat PTSD and/or sleep disorders.

Central disorders of hypersomnolence: diagnostic discrepancies between military and civilian sleep centers

STUDY OBJECTIVES

The majority of active-duty service members obtain insufficient sleep, which can influence diagnostic evaluations for sleep disorders, including disorders of hypersomnolence. An incorrect diagnosis of hypersomnia may be career ending for military service or lead to inappropriate medical care. This study was conducted to assess the rates at which narcolepsy (Nc) and idiopathic hypersomnia (IH) are diagnosed by military vs civilian sleep disorders centers.

METHODS

This retrospective study utilized claims data from the Military Health System Data Repository. The analyses compared diagnostic rates of military personnel by provider type-either civilian provider or military provider-from January 1, 2016 to December 31, 2019. Three diagnostic categories for Nc and IH: Nc or IH, Nc only, and IH only, were assessed with multivariate logistic regression models.

RESULTS

We found that among service members evaluated for a sleep disorder, the odds ratios of a positive diagnosis at a civilian facility vs a military facility for Nc or IH was 2.1, for Nc only was 2.1, and IH only was 2.0 over the 4-year period.

CONCLUSIONS

Civilian sleep specialists were twice as likely to diagnose central disorders of hypersomnolence compared to military specialists. Raising awareness about this discrepancy is critical given the occupational and patient care-related implications of misdiagnoses.

CITATION

Thomas CL, Vattikuti S, Shaha D, et al. Central disorders of hypersomnolence: diagnostic discrepancies between military and civilian sleep centers. J Clin Sleep Med. 2022;18(10):2433-2441.

Diagnosing narcolepsy in the active duty military population

PURPOSE

Narcolepsy type I and type II are central hypersomnias characterized by excessive daytime sleepiness and nocturnal sleep disruptions. These rare disorders make the diagnosis complex, as multiple sleep disorders are known to cause false-positive results on testing. There is a high incidence of sleep disorders in the military, and the diagnosis of narcolepsy can have serious career implications. This study looked to assess for the presence of confounding disorders in patients previously diagnosed with narcolepsy.

METHODS

We conducted a retrospective analysis of patients aged 18-65 previously diagnosed with narcolepsy at an outside facility, referred for repeat evaluation at the Wilford Hall Sleep Disorders Center. Previous test results from the time of original diagnosis were reviewed if available and compared with repeat evaluation which included actigraphy, in-laboratory polysomnography, and multiple sleep latency testing.

RESULTS

Of the 23 patients, 2 (9%) retained a diagnosis of narcolepsy after repeat testing. Ten patients (43%) had insufficient sleep syndrome, five (22%) had significant circadian rhythm sleep-wake disorders, and nine (39%) patients were diagnosed with mild obstructive sleep apnea (OSA). Four of the nine patients with OSA (44%) had supine predominant OSA.

CONCLUSION

Diagnostic testing for narcolepsy may be influenced by the presence of comorbid sleep disorders including sleep-disordered breathing, insufficient sleep duration, and circadian misalignment which are common in active military personnel. This study emphasizes the importance of excluding these comorbid diagnoses in this population.

The Epworth Sleepiness Scale in Service Members with Sleep Disorders

INTRODUCTION

Excessive daytime sleepiness affects an estimated 20% of the general population. While the prevalence of sleepiness in the military is largely unknown, it is well established that short sleep duration is endemic. The reasons for this include: the demanding nature of their duties, shift work and 24-hour duty periods, deployments and exigencies of military service as well as sleep disorders. The Epworth Sleepiness Scale (ESS) is the most widely used sleep questionnaire and provides a self-assessment of daytime sleepiness. To date the clinical utility of this questionnaire in differentiating sleep disorders in military patients with sleep disorders has never been evaluated.

MATERIALS AND METHODS

The primary aim of this manuscript was to assess if Epworth Sleepiness Scale (ESS) scores differed between military personnel with insomnia, obstructive sleep apnea (OSA), comorbid insomnia/obstructive sleep apnea (COMISA), and a group with neither insomnia nor obstructive sleep apnea (NISA). This study assessed the clinical utility of the ESS in differentiating sleep disorders amongst a sample (N = 488) of U.S. military personnel with insomnia (n = 92), OSA (n = 142), COMISA (n = 221), and a NISA group (n = 33) which served as the control population.

RESULTS

In the present sample, 68.4% of service members reported excessive daytime sleepiness (EDS) with an ESS > 10. ESS scores differed between military personnel with COMISA (13.5 ± 4.83) and those with OSA only (11.5 ± 4.08; p < 0.001) and the NISA group (9.46 ± 4.84; p < 0.001). Also, ESS scores differed between patients with insomnia only (13.0 ± 4.84) and the NISA group (p < 0.01).

CONCLUSIONS

Overall, the ESS had poor ability to differentiate sleep disorders. In military personnel, the ESS appears elevated in the most common sleep disorders, likely due to their insufficient sleep, and does not help to differentiate OSA from insomnia. Further studies are required to validate this questionnaire and determine an appropriate threshold value for abnormal sleepiness in the military population.

The association of insomnia and sleep apnea with deployment and combat exposure in the entire population of US army soldiers from 1997 to 2011: a retrospective cohort investigation

Since 2001, the United States has been engaged in the longest and most expensive overseas conflict in its history. Sleep disorders, especially insomnia and obstructive sleep apnea (OSA), are common in service members and appear related to deployment and combat exposure, but this has not been systematically examined. Therefore, the incidence of clinically diagnosed insomnia and OSA from 1997 to 2011 in the entire population of US Army soldiers was determined and associations of these disorders with deployment and combat exposure examined. This observational retrospective cohort study linked medical, demographic, deployment, and combat casualty data from all active duty US Army soldiers serving from 1997 to 2011 (n = 1 357 150). The mediating effects of multiple known comorbid conditions were considered. From 2003 to 2011, there were extraordinary increases in incidence of insomnia (652%) and OSA (600%). Factors increasing insomnia risk were deployment (risk ratio [RR] [deployed/not deployed] = 2.06; 95% confidence interval [CI], 2.04-2.08) and combat exposure (RR [exposed/not exposed] = 1.20; 95% CI, 1.19-1.22). Risk of OSA was increased by deployment (RR [deployed/not deployed] = 2.14; 95% CI, 2.11-2.17), but not combat exposure (RR [exposed/not exposed] = 1.00; 95% CI, 0.98-1.02). These relationships remained after accounting for other factors in multivariable analyses. A number of comorbid medical conditions such as posttraumatic stress disorder and traumatic brain injury mediated a portion of the association between the sleep disorders and deployment. It is essential to determine underlying mechanisms responsible for these very large increases in insomnia and OSA and introduce effective preventive measures.

Psychiatric disorders moderate the relationship between insomnia and cognitive problems in military soldiers

BACKGROUND

There has been a great deal of research on the comorbidity of insomnia and psychiatric disorders, but much of the existing data is based on small samples and does not assess the full diagnostic criteria for each disorder. Further, the exact nature of the relationship between these conditions and their impact on cognitive problems are under-researched in military samples.

METHOD

Data were collected from the All Army Study of the Army Study to Assess Risk and Resilience in Service members (unweighted N = 21, 449; weighted N = 674,335; 18-61 years; 13.5% female). Participants completed the Brief Insomnia Questionnaire to assess for insomnia disorder and a self-administered version of the Composite International Diagnostic Interview Screening Scales to assess for psychiatric disorders and cognitive problems.

RESULTS

Military soldiers with current major depressive episode (MDE) had the highest prevalence of insomnia disorder (INS; 85.0%), followed by current generalized anxiety disorder (GAD; 82.6%) and current posttraumatic stress disorder (PTSD; 69.7%), respectively. Significant interactions were found between insomnia and psychiatric disorders; specifically, MDE, PTSD, and GAD status influenced the relationship between insomnia and memory/concentration problems.

LIMITATIONS

Cross-sectional nature of the assessment and the absence of a comprehensive neurocognitive battery.

CONCLUSION

Psychiatric disorders moderated the relationship between insomnia and memory/concentration problems, suggesting that psychiatric disorders contribute unique variance to cognitive problems even though they are associated with insomnia disorder. Results highlight the importance of considering both insomnia and psychiatric disorders in the diagnosis and treatment of cognitive deficits in military soldiers.

Gender differences in sleep disorders in the US military

OBJECTIVES

The purpose of this study is to compare sleep disorders between male and female military personnel. Comorbid behavioral health disorders and chronic pain were also studied in relation to sleep disorders.

DESIGN

We conducted a retrospective review of military personnel who underwent a sleep medicine evaluation and an in-laboratory attended polysomnography. Initial sleep questionnaires, demographics, polysomnographic variables, and comorbid disorders of interest were reviewed and compared for each sex.

SETTING

All patients were referred to the Wilford Hall Ambulatory Surgical Center Sleep Disorders Center for evaluation of sleep disturbance.

PARTICIPANTS

Our cohort consisted of 209 military personnel with 51.7% men. The cohort was relatively young with a mean age of 34.3 years. Men had a significantly higher body mass index at 29.4 vs 27.3 in women.

RESULTS

Insomnia was diagnosed in 72 women and 41 men (P< .001), whereas obstructive sleep apnea (OSA) was diagnosed in 92 men and 50 women (P< .001). Depression and anxiety were more common in women. Women had an average of 1.76 ± 1.36 comorbid conditions compared with 1.08 ± 1.19 in men. In patients diagnosed with both insomnia and OSA, women were more likely to have post-traumatic stress disorder, depression, and anxiety. Neither the Epworth Sleepiness Scale (12.8 ± 4.88) nor the Insomnia Severity Index (16.9 ± 5.33) differed between sexes.

CONCLUSIONS

Gender-related differences in sleep disorders are present in active-duty personnel. Behavioral health disorders were frequent comorbid disorders, and women diagnosed with both insomnia and OSA manifested greater psychiatric comorbidity. The frequent association between sleep and behavioral health disorders in military personnel requires further study.

Critical questions: Advancing the health of female Veterans

PURPOSE

Women are the fastest growing Veteran population in the United States and many receive all or part of their health care outside of the Department of Veterans Affairs (VA). The purpose of this article is to review the healthcare issues of women Veterans and discuss implications for care.

DATA SOURCES

Review of selected literature, VA resources and guidelines, and expert opinion.

CONCLUSIONS

Few providers are aware of the impact military service has on the health of women and fail to ask the all-important question, "Have you served in the military?" Recognizing women's military service can reveal important information that can answer perplexing clinical questions, aid in designing comprehensive plans of care, and enable women to receive the assistance needed to address complex physical and psychosocial issues to improve the quality of their lives.

IMPLICATIONS FOR PRACTICE

There are gender disparities related to physical health conditions, mental health issues, environmental exposures, and socioeconomic factors that contribute to female Veterans' vulnerabilities. Many of the health conditions, if recognized in a timely manner, can be ameliorated and shift the health trajectory of this population. Clinicians play a critical role in identifying health risk and helping female Veterans start the sometimes arduous journey toward wellness. Discovering and acknowledging women's military history is critical in ensuring quality care and appropriate decision making.